getSupportedEfforts() intersected explicit model.thinking metadata
with heuristic capability inference from known model IDs. For custom
OpenAI-compatible proxy models that intentionally override thinking
levels in models.yml, that intersection dropped xhigh, so request
construction stopped treating xhigh as supported and the outgoing
payload lost the high-effort marker. Trust the explicit metadata when
it is present and fall back to inference only otherwise.
Fixes#969
can1357
ef410f0f7c